© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2355
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prisonniers
    -0.77
     générations
    -0.73
     réfugiés
    -0.72
    AndEndTag
    -0.72
     émissions
    -0.70
     blessés
    -0.69
     leçons
    -0.68
     prêtres
    -0.65
     dépens
    -0.64
     travailleurs
    -0.64
    POSITIVE LOGITS
     all
    0.59
     causes
    0.57
    Климат
    0.54
     Lightboxes
    0.54
     ways
    0.54
     challenges
    0.53
     environments
    0.53
     compromises
    0.51
     opportunities
    0.50
     jsPsych
    0.50
    Activations Density 0.001%

    No Known Activations